Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1530 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3960. Min Range: -6.3960
Max Act: 6.3960. Min Act: -0.1700
Data Index: 8673161 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3960. Min Range: -6.3960
Max Act: 6.2085. Min Act: -0.1700
Data Index: 5170659 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3960. Min Range: -6.3960
Max Act: 6.1773. Min Act: -0.1700
Data Index: 7086838 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3960. Min Range: -6.3960
Max Act: 6.0523. Min Act: -0.1700
Data Index: 3037458 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.9898. Min Act: -0.1700
Data Index: 6070424 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.9898. Min Act: -0.1700
Data Index: 2707283 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.9898. Min Act: -0.1700
Data Index: 1297639 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.9898. Min Act: -0.1700
Data Index: 4592267 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.9273. Min Act: -0.1700
Data Index: 2820774 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.8960. Min Act: -0.1700
Data Index: 3789459 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.9585. Min Act: -0.1700
Data Index: 3789463 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.8960. Min Act: -0.1700
Data Index: 4444506 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.8648. Min Act: -0.1700
Data Index: 6344282 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.8960. Min Act: -0.1700
Data Index: 1080569 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.8960. Min Act: -0.1700
Data Index: 5015264 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.8960. Min Act: -0.1700
Data Index: 1869933 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.8960. Min Act: -0.1700
Data Index: 7404813 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.8648. Min Act: -0.1700
Data Index: 1582343 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.8960. Min Act: -0.1700
Data Index: 4988240 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.8960. Min Act: -0.1700
Data Index: 299550 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19